Atlas / Skills / every-app / Deslop

DeslopCAUTION

skills/every-app/deslop

Open source alternative to Semrush and Ahrefs

Verdict
CAUTION
Grade
B
Trust score
89 /100
Version
—
Hosts
—
License
MIT
Stars
24,463
01

Overview

Open source alternative to Semrush and Ahrefs

Read from source at commit 96aa192541caOBSERVED · 2026-10-22
Advertisement
02

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: deslop
description: Remove AI writing patterns from prose so it reads like a person wrote it. Use when writing, editing, or reviewing user-facing text (blog posts, docs, marketing copy, PR descriptions), or when asked to "deslop", "de-AI", or "make it sound human".
metadata:
  internal: true
---

# Deslop

Make prose sound like a specific person wrote it. Fix each tell by stating the underlying claim plainly, not by swapping in a new flourish.

## Cut or rewrite

- Filler: throat-clearing ("Here's the thing:"), emphasis crutches ("Let that sink in."), meta-commentary ("In this section, we'll explore..."), "It's worth noting," and business jargon ("navigate the landscape," "leverage").
- Staged contrasts like "Not X. Y." or "It's not X, it's Y." State Y.
- Manufactured rhythm: dramatic fragments ("Speed. That's it."), rhetorical questions answered right away ("The result? Devastating."), three-part phrasing that exists only for cadence ("fast, simple, and powerful"), and paragraphs that end on a one-liner restating the paragraph.
- AI vocabulary: "delve," "tapestry," "quietly," "serves as," "highlighting its importance," invented concept labels ("the supervision paradox"), and inflated stakes.
- Vagueness: declaratives that name nothing ("The reasons are structural"), "experts argue" with no name, and "every," "always" or "never" doing vague work.
- False agency, where a thing does a person's verb ("the complaint becomes a fix"). Name who did it.
- Signposting: announcing what you're about to say, then summarizing what you said. "In conclusion." "Despite these challenges."
- Formatting tells: em dashes, unicode arrows, and lists where every item opens with a bolded keyword.

## Keep

Specifics (names, numbers, examples), "you" for the reader in blog posts, varied sentence length, and short plain lines that carry information. Keep bullet points and numbered steps for actions and instructions; don't fold them back into paragraphs. When editing someone else's writing, keep their voice.

## Example

Before: "Here's the thing: most pipelines break in production. Not because the code is bad. Because the data is bad. Let that sink in."

After: "Most pipelines break in production. The code runs fine. The data doesn't match the assumptions baked into it."

Adapted from [stephenturner/skill-deslop](https://github.com/stephenturner/skill-deslop) (MIT, see LICENSE).
03

Trust audit

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (5)

MEDIUMInventory / provenance · inv.symlink · CWE-1104
.claude/skills/create-repo-skill
.claude/skills/create-repo-skill
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.claude/skills/deslop
.claude/skills/deslop
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.claude/skills/evaluate-skill
.claude/skills/evaluate-skill
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.claude/skills/merge-ready
.claude/skills/merge-ready
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.claude/skills/observability-triage
.claude/skills/observability-triage
Why it matters. link not followed

Gates applied: no_behavioural_pass.

Audited 2026-10-22 · audit v0.4.1 · source sha 96aa192541cafull audit observations/trust-audit/skill/every-app__deslop.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-2296aa192541caCAUTIONB89first audit
05

Questions

What does the deslop — every-app/open-seo skill do?

Open source alternative to Semrush and Ahrefs

Is deslop — every-app/open-seo safe to install?

With care. The audit graded it B (89/100) and found 5 things worth knowing before you trust this skill, listed below with the exact line each was found on.

What can deslop — every-app/open-seo access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (96aa192541ca), read on 2026-10-22. The repository is watched, and a new audit runs when it changes — this is the first audit.

Add this badge to your README

Shows this page's audit result and links back to it. It updates when the audit does.

ModelsAtlas audit badge

Markdown
[![ModelsAtlas audit: Deslop](https://modelsatlas.com/skills/every-app/deslop/badge.svg)](https://modelsatlas.com/skills/every-app/deslop/)

Not your listing, or something out of date? Claim or update your listing.

Advertisement